"What I'm more concerned about is that people with some chronic medication conditions, such as underlying heart disease or diabetes, are not getting vaccinated".
Traditional surveillance reporting takes up to three weeks, meaning response measures - such as deploying vaccines or anti-virals and advising patients to stay at home - can often lag.
Across each state, data from Fitbit trackers helped improve influenza predictions.
The virus still remains widespread in almost every state, with high levels of activity in 32 states. For example, media coverage of influenza alerting people to an outbreak makes it impossible to separate the behavior of people who have the flu from the so-called "worried well" who search for information online during epidemic periods.
Radin says her team plans to do a perspective study.
What did the study involve?
The researches also didn't have any data on children and their heart rates.
Barca top the Money League with record breaking revenue
The importance of European football was underscored by the fact that TV broadcast revenues make up 44% of clubs' income on average.
"Influenza is affecting young people more this season than previous years". Users were a mean age of around 43 and 60% were women.
From March 2016 to March 2018, the researchers examined data from 200,000 users in New York, California, Texas, Illinois and Pennsylvania. And while there are many reasons why someone's resting heart rate might be elevated aside from flu - lack of sleep, stress, weight gain - Radin found that, for a large population, the spikes in heart rate correlated with historical flu data.
Researchers tracked deviations in heart rate and sleep patterns, which tend to change when a person has the flu and compared that data to flu-like illness rates reported by the Centers for Disease Control and Prevention.
What did the results show? The actual number is higher; 22 of the state's 120 county health departments did not report.
In most cases, week-to-week changes in the proportion of people with abnormal data were associated with week-to-week changes in ILI rates.
Radin notes that there were a few limitations to their study, but they're at the beginning stages of building a model that will help with real-time flu predictions.
The researchers concluded: "Activity and physiological trackers are increasingly used in the U.S. and globally to monitor individual health. In the future, as these devices improve, and with access to 24/7 real-time data, it may be possible to identify rates of influenza on a daily instead of weekly basis".
In addition, weekly resting heart rate averages include days when an individual is both sick and not sick, and this may result in underestimation of illness by lowering the weekly averages.